no code implementations • 7 Dec 2014 • Krzysztof Chalupka, Pietro Perona, Frederick Eberhardt
We provide a rigorous definition of the visual cause of a behavior that is broadly applicable to the visually driven behavior in humans, animals, neurons, robots and other perceiving systems.
no code implementations • 26 Oct 2015 • Krzysztof Chalupka, Michael Dickinson, Pietro Perona
Looming has been proposed as the main monocular visual cue for detecting the approach of other animals and avoiding collisions with stationary obstacles.
no code implementations • 25 Dec 2015 • Krzysztof Chalupka, Pietro Perona, Frederick Eberhardt
We formalize the connection between micro- and macro-variables in such situations and provide a coherent framework describing causal relations at multiple levels of analysis.
no code implementations • 30 May 2016 • Krzysztof Chalupka, Tobias Bischoff, Pietro Perona, Frederick Eberhardt
We show that the climate phenomena of El Nino and La Nina arise naturally as states of macro-variables when our recent causal feature learning framework (Chalupka 2015, Chalupka 2016) is applied to micro-level measures of zonal wind (ZW) and sea surface temperatures (SST) taken over the equatorial band of the Pacific Ocean.
no code implementations • 4 Nov 2016 • Krzysztof Chalupka, Frederick Eberhardt, Pietro Perona
We propose a method to classify the causal relationship between two discrete variables given only the joint distribution of the variables, acknowledging that the method is subject to an inherent baseline error.
no code implementations • 8 Feb 2017 • Mohammad Taha Bahadori, Krzysztof Chalupka, Edward Choi, Robert Chen, Walter F. Stewart, Jimeng Sun
In application domains such as healthcare, we want accurate predictive models that are also causally interpretable.
1 code implementation • 8 Apr 2018 • Krzysztof Chalupka, Pietro Perona, Frederick Eberhardt
The test is based on the idea that when $P(X \mid Y, Z) = P(X \mid Y)$, $Z$ is not useful as a feature to predict $X$, as long as $Y$ is also a regressor.
1 code implementation • CVPR 2020 • Biagio Brattoli, Joseph Tighe, Fedor Zhdanov, Pietro Perona, Krzysztof Chalupka
Our training procedure builds on insights from recent video classification literature and uses a trainable 3D CNN to learn the visual features.
Ranked #4 on Zero-Shot Action Recognition on ActivityNet